BVI-SynTex : A Synthetic Video Texture Dataset for Video Compression and Quality Assessment
- Submitting institution
-
University of Bristol
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 244161890
- Type
- D - Journal article
- DOI
-
10.1109/TMM.2020.2976591
- Title of journal
- IEEE Transactions on Multimedia
- Article number
- -
- First page
- 26
- Volume
- 23
- Issue
- -
- ISSN
- 1520-9210
- Open access status
- Compliant
- Month of publication
- February
- Year of publication
- 2020
- URL
-
-
- Supplementary information
-
-
- Request cross-referral to
- -
- Output has been delayed by COVID-19
- No
- COVID-19 affected output statement
- -
- Forensic science
- No
- Criminology
- No
- Interdisciplinary
- No
- Number of additional authors
-
3
- Research group(s)
-
C - Visual Information Lab
- Citation count
- 1
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This paper is the first to develop a parameterisable dataset for the study and evaluation of compression performance on textured video content. It applies texture modelling from computer graphics alongside visual perception assessments to ensure domain coverage, suitable for deep learning applications. The work was performed as part of Katsenou’s Leverhulme Early Career Fellowship (ECF-2017-413). The paper is supported by an open dataset [link: 10.5523/bris.320ua72sjkefj2axcjwz7u7yy9] that includes both objective and subjective evaluation quality metadata alongside the synthesized sequences. Although only recently published it has already been used by other groups (e.g. 10.1109/QoMEX48832.2020.9123131).
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -